Sign in

Christian Bluethgen

@cxbln.bsky.social
521 followers 281 following 52 posts

Radiologist, Scientist & Faculty @ Stanford, Stanford AIMI | #RadSky #ChestRad 🫁🫀 🩻

PostsRepliesMedia
Christian Bluethgen @cxbln.bsky.social · 14/02/2026
🔥 So much in this paper: CT RATE (one of the largest public chest CT/text report datasets), CT-CLIP (a 3D chest CT foundation model) and CT-CHAT, a conversational model building on CT-CLIP @ibrahimethem.bsky.social
000
Reposted by Christian Bluethgen
Christian Bluethgen @cxbln.bsky.social · 30/10/2025
🚨 Agentic Systems in Radiology Everyone’s talking about agents🕵️‍♀️🕵️‍♂️ — but what happens when you bring them into real clinical workflows? Our new preprint explores the design, applications, challenges, and evaluation of LLM-based agents and agentic workflows in radiology 👇 arxiv.org/abs/2510.09404
182
Christian Bluethgen @cxbln.bsky.social · 30/10/2025
With amazing colleagues: @stanfordmedicine.bsky.social @stanfordaimi.bsky.social @curtlanglotz.bsky.social @akshay-chaudhari.bsky.social; @krauthammerlab.bsky.social; @ethz.ch @michaelmoor.bsky.social; @rwth.bsky.social @danieltruhn.bsky.social; @tudresden.bsky.social @jnkt.bsky.social & HOPPR
010
Christian Bluethgen @cxbln.bsky.social · 30/10/2025
🚨 Agentic Systems in Radiology Everyone’s talking about agents🕵️‍♀️🕵️‍♂️ — but what happens when you bring them into real clinical workflows? Our new preprint explores the design, applications, challenges, and evaluation of LLM-based agents and agentic workflows in radiology 👇 arxiv.org/abs/2510.09404
182
Reposted by Christian Bluethgen
IAMJB @iamjbd.bsky.social · 09/06/2025
💥 We unveil our paper accepted at the #ACL2025 Main Conference: Automated Structured Report Generation Let's revisit automated radiology report generation for CXR. Free-form reports make it hard for AI systems to learn accurate generation, and even harder to evaluate. 🧵👇 @StanfordAIMI @hopprai
173
Reposted by Christian Bluethgen
Woojin Kim, MD @woojinkim.com · 05/05/2025
👍 If you're interested in #LLMs in #radiology, this is a recommended read! 💯 While the article focuses primarily on LLMs, as the authors recommended, "Keep an eye on [large multimodal models]". 👉 pubs.rsna.org/doi/10.1148/... #RadiologyAI #AIStrategy #LMMs
041
Reposted by Christian Bluethgen
Ethan Mollick @emollick.bsky.social · 04/05/2025
When reading AI benchmarks, aside from the fact that many of the AIs are (accidentally or on purpose) trained on the test set, many tests are just bad. MMLU likely maxes out at 90% or so because so many of the questions in it are just wrong. It is also uncalibrated in difficulty across questions.
0273
Christian Bluethgen @cxbln.bsky.social · 03/04/2025
LLMs formally pass the Turing test arxiv.org/abs/2503.23674
arxiv.org
Large Language Models Pass the Turing Test
We evaluated 4 systems (ELIZA, GPT-4o, LLaMa-3.1-405B, and GPT-4.5) in two randomised, controlled, and pre-registered Turing tests on independent populations. Participants had 5 minute conversations s...
040
Christian Bluethgen @cxbln.bsky.social · 01/04/2025
lot of folks talking about MCP and developers rushing to support it - but it does seem a bit like hype-y. interesting perspective: hardcoresoftware.learningbyshipping.com/p/230-mcp-it...
hardcoresoftware.learningbyshipping.com
230. MCP - It's Hot, But Will It Win?
There's a long history of "middleware" in our industry. Everyone wants it. There's always a hot one, but it rarely makes to the finish line and often disappoints.
010
Christian Bluethgen @cxbln.bsky.social · 12/03/2025
that's a first :O
110
Christian Bluethgen @cxbln.bsky.social · 10/03/2025
arxiv.org/abs/2502.19634
arxiv.org
MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
Reasoning is a critical frontier for advancing medical image analysis, where transparency and trustworthiness play a central role in both clinician trust and regulatory approval. Although Medical Visu...
120
Reposted by Christian Bluethgen
TechCrunch @techcrunch.com · 06/03/2025
A quarter of startups in YC’s current cohort have codebases that are almost entirely AI-generated
tcrn.ch
A quarter of startups in YC’s current cohort have codebases that are almost entirely AI-generated
With the release of new AI models that are better at coding, developers are increasingly using AI to generate code. One of the newest examples is the current batch of Y Combinator, the storied Silicon Valley startup accelerator. A quarter of the W25…
3166
Reposted by Christian Bluethgen
Tugba Akinci D'Antonoli @tugbaakinci.bsky.social · 01/03/2025
Chaired two insightful sessions at #ECR2025 today! "Standardization and Reporting in AI Research" with experts Hans Reitsma Mike Klontzas Annika Reinke "How to Use ChatGPT for Academic and Administrative Tasks" Andreas S. Brendlin @cxbln.bsky.social and Ghizlane Lembarki @myesr.bsky.social
061
Christian Bluethgen @cxbln.bsky.social · 23/02/2025
still thinking about this interaction with Claude (Oct '24) from time to time
000
Christian Bluethgen @cxbln.bsky.social · 05/02/2025
r1ing away on an ordinary machine .. straight out of Kahnemans lesser known book "Thinking .. mostly slow"
020
Christian Bluethgen @cxbln.bsky.social · 05/02/2025
For Germans unable to vote locally, it is easy to partake, here's how: www.bundesregierung.de/breg-de/schw...
bundesregierung.de
Wahlwissen: Briefwahl | Bundesregierung
Wer am Wahltag zur Bundestagswahl 2025 verhindert ist, kann vorab per Briefwahl wählen. Alle wichtigen Informationen zur Briefwahl im Überblick.
010
Christian Bluethgen @cxbln.bsky.social · 02/02/2025
010
Reposted by Christian Bluethgen
Jay Alammar @jayalammar.bsky.social · 27/01/2025
The Illustrated DeepSeek-R1 Spent the weekend reading the paper and sorting through the intuitions. Here's a visual guide and the main intuitions to understand the model and the process that created it. newsletter.languagemodels.co/p/the-illust...
17523
Christian Bluethgen @cxbln.bsky.social · 22/01/2025
it's a journey
010
Christian Bluethgen @cxbln.bsky.social · 19/01/2025
how’d you guess?
000
Christian Bluethgen @cxbln.bsky.social · 07/01/2025
another excellent blog post by @chiphuyen.bsky.social, this time on #agents huyenchip.com/2025/01/07/a...
huyenchip.com
Agents
Intelligent agents are considered by many to be the ultimate goal of AI. The classic book by Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (Prentice Hall, 1995), defines ...
010
Reposted by Christian Bluethgen
Gaël Varoquaux @gaelvaroquaux.bsky.social · 19/12/2024
People: please don't ML for the sake of ML. I keep seeing manuscripts using fancy machine learning on brain-imaging data, where, in my opinion (having processed a lot of brain-imaging data), the method is way too complex for the richness of the data. Fancier is not better per se
58815
Christian Bluethgen @cxbln.bsky.social · 26/12/2024
my wl: - fewer low-hanging proof-of-concept studies (yes, it works for your specialty/organ/classification, too) - fewer head-to-head model comparisons (yes, llama 3.1 was better than llama 2 for your case, but peer review took 8 months, now there’s llama 4) - instead: RCTs, relevant outcomes
182
Reposted by Christian Bluethgen
TechCrunch @techcrunch.com · 24/12/2024
The promise and perils of synthetic data
tcrn.ch
The promise and perils of synthetic data
Is it possible for an AI to be trained just on data generated by another AI? It might sound like a harebrained idea. But it’s one that’s been around for quite some time — and as new, real data is increasingly hard to come by, it’s been gaining traction.…
12812
Christian Bluethgen @cxbln.bsky.social · 22/12/2024
thanks for sharing
000
Christian Bluethgen @cxbln.bsky.social · 22/12/2024
"productization requires [standardization in development and deployment], which is antithetical to research. [...] PhDs are supposed to come up with innovative ideas, validate these ideas, report the findings to the community by writing papers and then move on." [slightly edited to fit post limits]
030
Christian Bluethgen @cxbln.bsky.social · 18/12/2024
A market research team's dream: gathering real-world use cases and improvement opportunities directly from natural product usage from: www.anthropic.com/research/clio
020
Reposted by Christian Bluethgen
Maarten van Smeden @maartenvsmeden.bsky.social · 16/12/2024
NEW PREPRINT A detailed overview of 32 popular predictive performance metrics for prediction models arxiv.org/abs/2412.10288
1119565
Christian Bluethgen @cxbln.bsky.social · 13/12/2024
010
Christian Bluethgen @cxbln.bsky.social · 13/12/2024
this method doesn’t rely on the pin 📌 emoji so it’s more private. instructions: bsky.app/profile/luci...
001
Christian Bluethgen @cxbln.bsky.social · 13/12/2024
bsky.app/profile/book...
bsky.app
120
Reposted by Christian Bluethgen
merve @merve.bsky.social · 13/12/2024
VLMs go MoE ✨ DeepSeek AI dropped three new commercially permissive vision LMs based on SigLIP encoder and their DeepSeek-MoE decoder 🐳 the models come in 1.0B, 2.8B and 4.5B active params 🥹 models seem to catch up with state-of-the-art with less active parameters! huggingface.co/collections/...
1405
Christian Bluethgen @cxbln.bsky.social · 11/12/2024
>> jamanetwork.com/journals/jam...
jamanetwork.com
Chatbot Confabulations Are Not Hallucinations
To the Editor Asa Raskin warned in the podcast The AI Dilemma that “when you invent a new technology, you uncover a new class of responsibility, and it’s not always obvious what those responsibilities...
020
Christian Bluethgen @cxbln.bsky.social · 11/12/2024
the only way to influence this future is to shape it — h/t @adamrodmanmd.bsky.social @fchollet.bsky.social
153
Christian Bluethgen @cxbln.bsky.social · 11/12/2024
120
Christian Bluethgen @cxbln.bsky.social · 10/12/2024
Join us tomorrow for the session "Future Frontiers in Health AI: Emerging Technologies and Innovations" at #AIPlusHealth24 #RadSky #Radiology #StanfordAIMI
050
Christian Bluethgen @cxbln.bsky.social · 09/12/2024
although hinting at the limitations of the modality is still hedging and does not add much; the modality is usually clear and to someone not understanding the limitations of the modality you would have to elaborate even further
010
Reposted by Christian Bluethgen
Radiology: Artificial Intelligence @radiology-ai.bsky.social · 01/12/2024
We thank our amazing reviewers for their time and expertise. This work cloud highlights the reviewers who contribute to @radiology-ai. Thank you, peer reviewers! #RSNA2024 #radiology #AI
1174
Reposted by Christian Bluethgen
Tan-Lucien Mohammed, MD, FACR @tlhm-md.bsky.social · 05/12/2024
Tree in bud nodularity on a CXR (via barium aspiration) 🫁 #radiology #radsky #chestrad @laurengroner.bsky.social @chestradiologist.bsky.social @mmestas.bsky.social @avrahamcoopermd.bsky.social
2141
Christian Bluethgen @cxbln.bsky.social · 05/12/2024
no pressure 😃
010
Christian Bluethgen @cxbln.bsky.social · 05/12/2024
I do dabble in Multi-1Ical Imaging occasionally
ChatGPT's rendition based on stored user information.
040
Christian Bluethgen @cxbln.bsky.social · 05/12/2024
although it does take the fun out of the game in this case ¯\_(ツ)_/¯
020
Reposted by Christian Bluethgen
uai2026 @auai.org · 04/12/2024
who needs to keep track of all the profiles of conferences in #AI and #ML on 🦋? go.bsky.app/SZEr8Jf
13320
Christian Bluethgen @cxbln.bsky.social · 04/12/2024
plus it’s going to be in Zurich 🇨🇭
020
Reposted by Christian Bluethgen
Arvind Narayanan @randomwalker.bsky.social · 02/12/2024
And chatbots aren't moral agents nor have ownership of the text they output, so they don't need to be credited. The proper thing to do when using a chatbot is to disclose it, for transparency, rather than cite it for attributing credit or signaling credibility. 4/
68714
Christian Bluethgen @cxbln.bsky.social · 03/12/2024
too soon
050
Christian Bluethgen @cxbln.bsky.social · 03/12/2024
the very same. also still have my notes 😃
120
Christian Bluethgen @cxbln.bsky.social · 03/12/2024
my (and probably many others’) entry point to ML research was this man's course, using Octave back then in 2016. so extremely honored to share an author list now with Prof. @andrewyng.bsky.social ! thank you
170
Christian Bluethgen @cxbln.bsky.social · 02/12/2024
esp. for a CXR that often takes less than a minute from opening it to signing the report. if the prelim report is subpar and I have to read, move back-and-forth between image and text and redact it, it would probably slow me down, leading to not adopting the tool. the improvement must be substantial
010